AI Model Serving Specialist

A company is looking for an AI Model Serving Specialist to operationalize AI workloads by deploying and optimizing model-serving platforms.

Key Responsibilities

Package and deploy ML / LLM models on platforms like Triton, vLLM, or KServe within Kubernetes clusters

Integrate models with Unified Inference API and ensure secure GPU resource allocation

Assist solution architects in onboarding customers and provide troubleshooting support

Required Qualifications

Hands-on experience with NVIDIA Triton, vLLM, or similar serving stacks

Strong knowledge of Kubernetes and GPU scheduling

Familiarity with VMware VCF9 and NSX-T networking

Proficiency in Python and containerization (Docker)

Understanding of observability stacks and FinOps principles